Statistical methods for seamless phase II/III design

The seamless phase II/III design combining phases II and III into a single trial has been shown growing interest for improving the efficiency of drug development, becoming most frequent adaptive type. It typically consists two stages, objectives being often different in each stage. primary are to select optimal experimental treatment group(s) first stage compare efficacy between selected control groups second In final analysis, appropriate statistical methods should be applied avoid increasing type I error rate selection bias. This paper reviews several that can designs. Especially, representative such as group sequential approach, combination test conditional function organized unified framework characteristics compared. As related topics, case where endpoints stages 1 2, method sample size calculation will also discussed. Examples actual applications presented.